Imaging of traumatic peripheral nerve injuries

Deep Learning-Based Knee MRI Classification for Common Peroneal Nerve Palsy with Foot Drop

Foot drop can have a variety of causes, including the common peroneal nerve (CPN) injuries, and is often difficult to diagnose. We aimed to develop a deep learning-based algorithm that can classify foot drop with CPN injury in patients with knee MRI axial images only. In this retrospective study, we included 945 MR image data from foot drop patients confirmed with CPN injury in electrophysiologic tests (n = 42), and 1341 MR image data with non-traumatic knee pain (n = 107). Data were split into training, validation, and test datasets using a 8:1:1 ratio. We used a convolution neural network-based algorithm (EfficientNet-B5, ResNet152, VGG19) for the classification between the CPN injury group and the others. Performance of each classification algorithm used the area under the receiver operating characteristic curve (AUC). In classifying CPN MR images and non-CPN MR images, EfficientNet-B5 had the highest performance (AUC = 0.946), followed by the ResNet152 and the VGG19 algorithms. On comparison of other performance metrics including precision, recall, accuracy, and F1 score, EfficientNet-B5 had the best performance of the three algorithms. In a saliency map, the EfficientNet-B5 algorithm focused on the nerve area to detect CPN injury. In conclusion, deep learning-based analysis of knee MR images can successfully differentiate CPN injury from other etiologies in patients with foot drop.

High-resolution ultrasound and magnetic resonance imaging of ulnar nerve neuropathy in the distal Guyon tunnel

OBJECTIVE

The aim of the present study is to describe the ultrasound (US) and magnetic resonance imaging (MRI) findings in patients with neuropathies affecting the deep (DB) and superficial (SB) branches of the Ulnar nerve (UN) and to investigate the potential role of imaging modalities in the diagnostic workup of these conditions.

MATERIALS AND METHODS

We screened our institutional imaging database to identify patients with a diagnosis of UN mononeuropathy, and among them, we reviewed the cases where US disclosed pathological findings affecting the UN terminal divisions. In this latter subgroup, we retrieved available data on MRI and electrodiagnostic tests performed by the patients during the diagnostic workup. All the patients were evaluated with US machines equipped with 17-5-MHz, 18-4-MHz, 24-8-MHz, or 22-8-MHz probes. MRI exams were performed on a 3-T unit equipped with a 64-channel head RF coil.

RESULTS

Among 166 patients with UN mononeuropathy, we retrieved 15 patients (9%) for which US detected pathological findings affecting the UN terminal divisions, consisting of 7 cases of DB neuropathy, 4 cases of SB neuropathy, and 4 cases of combined neuropathy involving both nerves. Seven (46.7%) patients were submitted to MRI to integrate US findings. Among patients with SB and DB neuropathies, imaging allowed the identification of 7 traumatic nerve injuries, 2 nerve tumors, and 6 entrapment neuropathies, including 4 cases of nerve compression by a ganglion cyst.

CONCLUSION

High-resolution US and MRI are accurate modalities for the investigation of patients with SB/DB neuropathy, can provide critical information on the cause of nerve damage, and guide therapeutic decisions.

CRITICAL RELEVANCE STATEMENT

High-resolution US and MRI are accurate modalities for the investigation of patients with superficial/deep branch of the ulnar nerve neuropathy. In the proper setting, US may be regarded as a first-line approach in patients with suspected neuropathies affecting these small branches.

KEY POINTS

• Neuropathies affecting the distal ulnar nerve often require multimodal investigations. • US and MRI can provide detailed morphological information about the terminal branches of the ulnar nerve. • US may be considered as a first-line approach in suspected distal ulnar nerve neuropathies.